Automated Generation of Consistent PDDL Domains using Large Language Models
Large Language Models can transform natural language domain descriptions into plausible PDDL markup, but ensuring consistency within the generated domains remains challenging. This paper presents a novel concept to significantly improve the quality of LLM-generated PDDL models by performing automated consistency checking during the generation process.
Latent Space Planning for Stochastic Systems: An Efficient Approach to Risk-Bounded Trajectory Optimization with Learned Dynamics
A "generate-and-test" approach to risk-bounded planning for autonomous mobile agents with learned, non-linear, stochastic dynamics. The method uses a variational autoencoder to learn an approximate linear latent dynamics model and performs trajectory optimization in the latent space, while a validator assesses the risk of the candidate trajectory and computes additional safety constraints.
HiCRISP: A Hierarchical Closed-Loop Robotic Intelligent Self-Correction Planner for Enhancing Adaptability in Dynamic Environments
HiCRISP is an innovative framework that enables robots to actively monitor and adapt their task execution by addressing both high-level planning errors and low-level action errors, thereby enhancing their overall robustness and adaptability in dynamic real-world environments.
Efficient Algorithms for Integrated Task and Motion Planning with Factored Optimization, Sampling, and Learning
This thesis presents novel algorithms that efficiently solve complex Task and Motion Planning (TAMP) problems by tightly integrating discrete task planning with continuous trajectory optimization, adaptively combining sampling and optimization methods, and accelerating computations using deep learning.
Automating Long-Horizon Robotic Tasks through Future-Predictive Success-or-Failure Classification
This paper proposes a future-predictive success-or-failure classification method to automatically obtain conditions required by optimization-based planning methods for long-horizon robotic tasks, eliminating the need for iterative trials and manual redesign.
Optimization-based Task and Motion Planning: Integrating High-level Task Planning and Low-level Motion Planning for Autonomous Robots
Optimization-based task and motion planning (TAMP) integrates high-level task planning and low-level motion planning to enable robots to effectively reason over long-horizon, dynamic tasks by defining goal conditions via objective functions and handling open-ended goals, robotic dynamics, and physical interaction between the robot and the environment.
Efficient Incremental Replanning for Feasible and Infeasible Linear Temporal Logic Task Specifications in Dynamic Environments
An incremental replanning algorithm that efficiently finds optimal solutions for both feasible and infeasible Linear Temporal Logic task specifications in dynamically changing environments.
© 2024 by Linnk AI